Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

31,456 Article Results

Automated bacteria and fungi classification using convolutional neural network on embedded system

10.11591/ijai.v15.i2.pp1132-1142
Tarik Bouganssa , Maryem Ait Moulay , Samar Aarabi , Abedelali Lasfar , Abdelatif EL Afia
In this study, we created and applied novel concepts for hardware-based image identification and categorization. For artificial intelligence (AI) and image recognition applications, this includes putting algorithms for recognizing colors, textures, and shapes into practice. Our contribution uses an embedded device with a camera and a microcomputer (Raspberry-Pi4 type) to replace the optical assessment of Petri dishes. Our object recognition system processes images efficiently by using a state-of-the-art kernel function and a new neighborhood architecture. Using the well-known convolutional neural network (CNN) architecture, YOLOv8, as a pre-trained model, we evaluated the proposed CNN-based method for object recognition in a number of demanding scenarios. Several Petri plates, uncontrolled settings, and different backgrounds and illumination were used to evaluate the technology. Our dynamic mode integrates a CNN network with an attention mask to highlight the traits of bacteria and fungi, ensuring robust recognition. We implemented our algorithm on a Raspberry Pi 400, connected to a CMOS 3.0 camera sensor and a human-machine interface (HMI) for instant display of results.
Volume: 15
Issue: 2
Page: 1132-1142
Publish at: 2026-04-01

Deep learning for early detection of cardiovascular diseases via auscultation sound classification

10.11591/ijai.v15.i2.pp1746-1761
Shreyas Kasture , Sudhanshu Maurya , Amit Kumar Sharma , Santhosh Chitraju Gopal Varma , Kashish Mirza , Firdous Sadaf Mohammad Ismail
Heart diseases are one of the most prominent causes of death globally, which requires immediate and accurate diagnosis. The auscultation methods used in conventional medical practice, where the doctor listens to the sounds produced by the body without intervention is very ineffective because of the limitations in the actual skills and perception of the doctor. The main goal of this project will be designing a mobile-based system for the early detection of cardiovascular disease (CVD) by utilizing deep learning for auscultation sound classification. The approach involves the use of deep learning structures to classify cardiac sounds into normal and abnormal patterns on its own. Wavelet transformations, time-frequency representations, and Mel frequency cepstral coefficients (MFCC) have been used in feature extraction. The ResNet152V2 model showed high classification performance with area under the receiver operating characteristic curve (AUROC) of 0.9797 and 0.9636 on two datasets. Contrary to that, data augmentation, hyperparameter optimization, attention mechanisms, as well as input-output residual connections, led to better functionality and interpretability. This research seeks to overcome the limitations of traditional stethoscope use through the incorporation of sophisticated algorithms and the availability of mobile technology that could result in early diagnosis and prevention of CVDs, especially in underprivileged areas.
Volume: 15
Issue: 2
Page: 1746-1761
Publish at: 2026-04-01

Genetic algorithm-based chicken manure weight prediction system development

10.11591/ijai.v15.i2.pp1247-1260
Rida Hudaya , Septriandi Wirayoga , Moechammad Sarosa , Muhammad Yusuf , Armanda Dwi Prayugo
This research presents design and implementation of internet of things (IoT) based monitoring and predictive system for evaluating chicken manure weight and environmental conditions in poultry housing. The proposed system integrates MQ-137 sensor for ammonia detection, DHT22 sensor for temperature and humidity measurement, and load cell modules for manure weight monitoring. All sensor data are transmitted in real time to cloud platform, enabling continuous environmental assessment. A 30-day experimental study was conducted using two controlled chicken drum models, each containing 15 broiler chickens and provided with different feed types to observe variations in manure production and air quality. Sensor calibration results indicate high accuracy, with average error of 0.31% for ammonia readings and 0.10% for manure weight measurement. Experimental findings show that feed type A generates lower manure weight, reduced ammonia concentration, and more stable temperature conditions compared to feed type B, suggesting improved feed efficiency and better overall chicken health. A genetic algorithm (GA) was employed to optimize regression model predicting manure weight using ammonia concentration and temperature as input features. The GA-optimized model achieved strong predictive performance, with root mean square error (RMSE) of 0.358 g and coefficient of determination (R2) value of 0.992. The results demonstrate that proposed system provides reliable, scalable, and data-driven solution for smart poultry monitoring and early health detection.
Volume: 15
Issue: 2
Page: 1247-1260
Publish at: 2026-04-01

A counter-centric binary-to-binary coded decimal and multiplexed seven-segment driver on an Artix-7 FPGA

10.12928/telkomnika.v24i2.27610
Ahmed Mohamed Abdellatif Abdelrahman; King Abdulaziz University Elngar , Muhamad S.; King Abdulaziz University Mauladdawilah , Tariq H. M.; King Abdulaziz University Alomary
This paper presents a complete field-programmable gate array (FPGA) implementation for showing a 4-bit binary value (0–15) as a two-digit decimal number on the Nexys-4 double data rate (DDR) seven-segment display. The design comprises: (i) a compact binary-to-binary-coded decimal (BCD) converter tailored to the 0–15 range; (ii) a seven-segment decoder for active-low, common-anode digits; and (iii) a counter-based clock-enable controller that time-multiplexes the digits at a rate chosen to be flicker-free yet energy-efficient. A simple timing model links the divider width , the number of digits , and the refresh rate . Simulation verified hazard-free switching and one-hot anode selection; hardware tests on the Nexys-4 DDR (100 MHz clock) confirmed the analysis. Selecting  yields  ms and  Hz, which removes ghosting while avoiding unnecessary high-frequency scanning. The system displays all inputs correctly and provides a clear sizing rule for wider inputs and more digits. The approach is fully synthesizable, resource-light, and portable to larger word-lengths and displays.
Volume: 24
Issue: 2
Page: 676-684
Publish at: 2026-04-01

Adaptive control of ball and beam system using SNA-PID combined with recurrent fuzzy neural network identifier

10.11591/ijai.v15.i2.pp1202-1210
Minh-Thanh Le , Chi-Ngon Nguyen
The ball and beam system is a nonlinear and inherently unstable single input, multiple-output (SIMO) system, which poses significant challenges for control design. Intelligent control algorithms are often applied to autonomously control complex systems when there are changes in parameters or the control environment. Therefore, in this paper, we research and develop two methods: proportional integral derivative (PID) and single neuron adaptive (SNA)-PID-recurrent fuzzy neural network identifier (RFNNI) to control the ball and beam system. Simulation results on MATLAB/Simulink show that the SNA-PID-RFNNI controller provides a more stable output signal than the traditional PID controller, with minimal overshoot and a settling time of about 15 seconds. Next, we will conduct real-time experiments on the object using the proposed algorithm through the MEGA2560 control board with an ultrasonic positioning mechanism.
Volume: 15
Issue: 2
Page: 1202-1210
Publish at: 2026-04-01

A comprehensive analysis of feature selection and XAI for machine learning classifiers to recognize guava disease

10.12928/telkomnika.v24i2.27599
Sujon Chandra; University of Frontier Technology, Bangladesh (UFTB) Sutradhar , Md. Mehedi; University of Frontier Technology Hasan
Recognizing and classifying diseases in guava is crucial for managing farms to keep crops healthy and increase harvest quality. Cultivators face the most severe challenges when it comes to recognizing and diagnosing guava fruit and leaf illnesses, a task that is nearly impossible to perform manually. This research focuses on developing a robust disease identification model using image data collected locally from guava trees. After data collection, various image processing techniques, including scaling and contrast enhancement, are utilized to make the data more suitable for use. K-means clustering is employed to quickly divide the images into groups, followed by the extraction of important characteristics. Two separate feature ranking approaches, analysis of variance (ANOVA) and least absolute shrinkage selection operator (LASSO), are used to select the best characteristics, identifying the 10 most important attributes. The adaptive boosting (AdaBoost) classifier achieves the highest accuracy among six classifiers for the top seven characteristics indicated by LASSO among the specified features. To enhance the model’s interpretability, two explanation methods, local interpretable model-agnostic explanations (LIME) and shapley additive explanations (SHAP), are employed to illustrate how the classifier reaches its conclusions. This approach not only simplifies disease identification but also clarifies the reasoning behind predictions, opening the door to real-world applications in detecting and preventing dangerous diseases.
Volume: 24
Issue: 2
Page: 574-587
Publish at: 2026-04-01

An intelligent and explainable IoT-Edge-Cloud architecture for real-time water quality monitoring

10.11591/ijai.v15.i2.pp1109-1120
Sara Bouziane , Badraddine Aghoutane , Aniss Moumen , Anas El Ouali , Ali Essahlaoui , Abdellah El Hmaidi
Continuous and reliable monitoring of water quality is critical for early detection of environmental deterioration, yet conventional monitoring approaches are often slow and lack timely data availability. This study proposes an intelligent and explainable internet of things (IoT)–Edge–Cloud architecture to monitor water quality in real time, using IoT sensing, edge based artificial intelligence (Edge AI), cloud-stream processing, and explainable artificial intelligence (XAI). The system calculates the water quality index (WQI) directly at the edge and predicts its evolution using a stacking ensemble model trained on physicochemical measurements taken from the Moulouya River Basin in Morocco. An explainability module based on Shapley additive explanations (SHAP) values gives a clearer image of the contribution of various parameters to WQI predictions, providing transparency of the features, which builds trust in the model’s output. The proposed architecture was implemented as an end-to-end prototype and validated using a simulation-based experimental that mimicked realistic sensor dynamics and connectivity interruptions. The experimental results show strong predictive performance (R² =0.945), stable system operations, and reliable interpretability highlighting the potential of the proposed approach for scalable, intelligent, and transparent environmental monitoring.
Volume: 15
Issue: 2
Page: 1109-1120
Publish at: 2026-04-01

Fetal organ detection using feature enhancement with attention and residual block

10.11591/ijai.v15.i2.pp1593-1604
Nuswil Bernolian , Siti Nurmaini , Ade Iriani Sapitri , Annisa Darmawahyuni , Muhammad Naufal Rachmatullah , Bambang Tutuko , Firdaus Firdaus
The rapid advancements in fetal ultrasonography have significantly enhanced prenatal diagnosis in recent years. Deep learning (DL) architectures have further streamlined the process of organ detection, improved diagnostic accuracy, and reduced observer dependency. This study proposes a computer-aided DL approach for fetal organ segmentation using the you only look once (YOLO) algorithm, a state-of-the-art method for object detection and image segmentation. This study identified and classified 15 fetal organs, including the umbilical vein, stomach, abdomen, brain (trans-cerebellum, trans-thalamic, and trans-ventricular regions), femur, head, thorax (chest cavity), heart (circumference, left atrium, left ventricle, right atrium, right ventricle), and aorta. We compared the performance of YOLOv7, YOLOv8, YOLOv9, and YOLOv11 architectures. The results showed that YOLOv9 outperformed YOLOv7, YOLOv8, and YOLOv11 achieving mAP50 and mAP95 scores of 91.90% and 94.50%, respectively. This performance surpasses previous studies that focused on classifying only a limited number of fetal organs.
Volume: 15
Issue: 2
Page: 1593-1604
Publish at: 2026-04-01

Enhanced VGG-19 model for rice plant disease detection and classification

10.11591/ijai.v15.i2.pp1691-1700
Aye Thida Win , Khin Mar Soe , Myint Myint Lwin
Rice is the main staple food and rice farming plays a crucial role in the agriculture sector of Myanmar. It is also an essential pillar in generating foreign income. However, rice diseases seriously reduced the rice production and quality. Early detection of rice diseases is one of the effective ways to reduce the disease spreading and increase yields. Most Myanmar farmers detect rice diseases based on visual judgment and their experience, which leads to delay in taking efficient action. To overcome this challenge, we intend to propose an enhanced rice plant disease classification model that contributes as artificial intelligence (AI) in Myanmar agriculture sector. The proposed model enhances original visual geometry group 19 (VGG-19) by integrating the algorithms: mixture of Gaussians 2 (MOG2), GrabCut, and relevance estimation with linear feature (RELIEF) for classification. It was trained on 6,326 rice plant images of Kaggle and Eastern Shan State and validated using 5-fold nested cross-validation. The training and testing of proposed model are followed as 80:20. The proposed model experimental result is (98.3%) and lowest standard deviation (0.004) across seven classes than the original VGG-19, MobileNet, Efficient Net, and RestNet50 respectively. Future work will expand dataset diversity, enhance early-stage disease prediction, and support mobile diagnostics for real-world agricultural application.
Volume: 15
Issue: 2
Page: 1691-1700
Publish at: 2026-04-01

Noise-suppression method for UAV-OFDM systems by introducing CV-VSS-NLMS algorithm and single-antenna architecture

10.12928/telkomnika.v24i2.27396
Walid; Université Abbes Laghrour Khenchela Lebbou , Laid; Université Abbes Laghrour Khenchela Chergui , Saad; Setif 1 University Ferhat Abbas Bouguezel
In this paper, we address the critical challenge of impulsive interference in orthogonal frequency division multiplexing (OFDM)-based unmanned aerial vehicle (UAV) communication systems, which can severely degrade data transmission reliability. Specifically, we propose a novel complex-valued variable step-size normalized least mean square (CV-VSS-NLMS) adaptive filtering algorithm dedicated for adaptive filtering of complex-valued signals, providing real-time, lightweight, and efficient impulsive-noise suppression for UAV-OFDM signals. In contrast, real-valued VSS-LMS filters treat the real and imaginary parts separately, resulting in poorer mean square error (MSE) convergence for complex signals. The algorithm is developed by efficiently adapting LMS-based filtering strategies to impulsive interference scenarios and adequately integrating prior concepts of electromagnetic pulse suppression within a well-designed single-antenna UAV architecture. This new configuration is especially suited for size, weight, and power-constrained UAV platforms, where reducing complexity is highly desirable. In contrast to conventional blind source separation approaches, the proposed solution ensures reliable communication without excessive processing demands, since it efficiently suppresses impulsive noise and greatly reduces the number of matrix operations. Simulation results demonstrate a significant improvement in bit error rate (BER), confirming that the proposed CV-VSS-NLMS technique provides a robust, dependable, and practical solution for modern UAV communication links.
Volume: 24
Issue: 2
Page: 407-419
Publish at: 2026-04-01

RBC_Frame_Net: a hybrid deep learning framework for detection of red blood cells in malaria diagnostic smear

10.11591/ijai.v15.i2.pp1486-1496
Muhammad Shameem P. , Mathiarasi Balakrishnan
Malaria continues to pose a major global health threat, especially in areas where timely and accurate diagnosis is essential for effective treatment. Conventional diagnostic techniques, such as manually examining Giemsa stained blood smears, are often time-intensive, laborious, and susceptible to human error. To overcome these challenges, this study presents red blood cell frame network (RBC_Frame_Net), a novel deep-learning framework that combines convolutional neural networks (CNNs) with transformer based architectures, augmented by attention mechanisms, for the automated identification of RBCs in malaria smear images. The framework leverages the convolutional block attention modules (CBAM)-UNet model for segmentation, enhancing both spatial and channel features through CBAM and integrates the detection transformer (DETR) to accurately detect and classify RBCs within the diagnostic images. The model achieved outstanding performance with a segmentation intersection over union (IoU) of 0.97, a Dice coefficient of 0.98, and near-perfect detection results (precision: 0.999, recall: 0.998, and mean average precision (mAP): 0.995). When compared to leading models such as YOLOv8, faster region-based convolutional neural network (Faster R-CNN), and EfficientDet-D3, and RBC_Frame_Net demonstrated superior accuracy and robustness. The inclusion of attention mechanisms and a hybrid architecture enhance its adaptability, making it well-suited for deployment in real-world, resource limited environments and positioning it as a valuable asset in automated malaria diagnostics.
Volume: 15
Issue: 2
Page: 1486-1496
Publish at: 2026-04-01

Business intelligence for measuring global systems for mobile communication provider performance

10.12928/telkomnika.v24i2.26293
Yusri Eli Hotman; Universitas Trisakti Turnip , Dedy; Trisakti University Sugiarto , Rina; Universitas Trisakti Fitriana , Yun-Chia; Yuan Ze University Liang
Internet access is getting easier in various places, including Indonesia. Telecommunication media are no longer dominated by the use of pulse signals but have shifted to relying on internet access. This study aims to create a data visualization of internet speed in Bekasi urban sub-districts using the business intelligence (BI) model with online analytical processing (OLAP). Clustering was carried out using two methods, namely the K-means and K-medoids methods which were selected based on the Davies Bouldin index (DBI) value. This study produced a visual data prototype from the results of clustering from the data mining process and was accompanied by supporting data in the form of information on the highest and lowest speeds in the studied sub-districts. The clustering process uses K-means for uploading data with a DBI value of 0.847, while the data download uses K-medoids with a DBI value of 0.871. The prototype displays observation data, maximum and minimum value information, and the clustering result. The functional test result for the prototype showed conformity with the requirements, while the validation test showed that the prototype passed the validation test with a score of 0.8833.
Volume: 24
Issue: 2
Page: 737-750
Publish at: 2026-04-01

Hybrid intrusion detection in IoT devices: a deep learning approach using Kitsune and quantized autoencoder

10.12928/telkomnika.v24i2.27316
Md. Rifat E; Comilla University Noor , Md. Tofael; Comilla university Ahmed , Dulal; Comilla University Chakraborty , Pintu Chandra; Comilla University Paul , Sohana; Comilla University Nowar , Rejwan; Comilla University Ahmed , Tanjina; Comilla University Akter
Internet of things (IoT) has been transforming the way to connect and communicate in smart homes, healthcare, and businesses so fast and rapidly around the world. But this growth has complicated security, because IoT devices are more likely to be hacked as they’re smaller, without even regular security practices, and under attack by more sophisticated threats. Traditional intrusion detection systems (IDS) are not functioning well in IoT environments as they are computationally expensive and struggle to accommodate the heterogeneous nature of IoT networks. This paper introduces a cross-domain intrusion detection based on adaptive adversarial training using Kitsune and quantized autoencoders (QAE) for anomaly detection and classification. The model is capable of capturing different attacking techniques, such as distributed denial of service (DDoS), Mirai botnet attacks, address resolution protocol (ARP) spoofing, and data exfiltration, by leveraging the reconstruction error generated by Kitsune autoencoders. The degree-based classification enables the system to dynamically categorize anomalies according to their severity, rendering the model exceptionally adaptive to various attacks. The anomalies are also classified into different types of attacks (normal, suspicious, and malicious) based on binarized error values. The approach achieves a high accuracy with an F1 score of 85.9% and supports real-time characterization to increase security in IoT scenarios.
Volume: 24
Issue: 2
Page: 452-465
Publish at: 2026-04-01

Hardware simulation of cooperative adaptive cruise control based on fuzzy logic

10.12928/telkomnika.v24i2.27466
Edi; Politeknik Negeri Bandung Rakhman , Noor Cholis; Politeknik Negeri Bandung Basjaruddin , Didin; Politeknik Negeri Bandung Saefudin , Rizky; Politeknik Negeri Bandung Hartono , Rachmad Imbang; Politeknik Negeri Bandung Tritjahjono
Cooperative adaptive cruise control (CACC) is a system designed to maintain a vehicle’s distance according to the driver’s preset value. It is an advancement of adaptive cruise control (ACC), which suffers from response delays when reacting to changes in the leading vehicle’s speed. CACC addresses this limitation by reducing response delay through the use of speed data from the preceding vehicle, obtained via wireless communication. In this research, the CACC system was simulated using a 1:10 scale remote-control (RC) car equipped with ultrasonic sensors and radio frequency (RF) communication. Speed control was implemented using a fuzzy logic controller with the Mamdani inference method, while an active steering assistance system was added to maintain lane alignment. Hardware simulation results demonstrate that the CACC system functions effectively and significantly improves the response time of the following vehicle when the leading vehicle changes speed. Experimental results show that the CACC maintained the desired following distance in 10 seconds, compared to 15 seconds for the ACC system.
Volume: 24
Issue: 2
Page: 685-695
Publish at: 2026-04-01

Dual-band performance enhancement of terahertz patch antennas via slotting method

10.12928/telkomnika.v24i2.27564
Bich Ngoc; Vietnam Aviation Academy Tran-Thi , Trong Hai; Vietnam Aviation Academy Le
Sixth-generation (6G) wireless networks are designed to provide ultra-high data rates with latencies as low as one microsecond, operating at frequencies higher than those used in fifth-generation (5G) networks. This study focuses on a compact and flexible dual-band terahertz (THz) rectangular patch antenna utilizing a slot cutting technique. The antenna features strategically placed rectangular slots on its patch, with dimensions of 1×1×0.1 mm. Its performance was simulated using computer simulation technology (CST) Studio Suite simulation software. The results indicate that the antenna operates at frequencies of 147.42 GHz and 202.5 GHz, achieving gains of 2.66 dB and 4.52 dB, respectively. Notably, the designed antenna demonstrates excellent impedance matching, as evidenced by deep return loss values of −19.818 dB and −44.776 dB. Furthermore, the findings report a voltage standing wave ratio (VSWR) of 1.01. This antenna design is suitable for applications in aerospace, 5G handheld devices, wireless communication, and THz medical imaging.
Volume: 24
Issue: 2
Page: 387-395
Publish at: 2026-04-01
1 2 3
...
2097 2098
Show 108 of 2098

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration